Bengali.AI: Handwritten Grapheme Classification Using PyTorch (Part-2)

In this video, I will show you how to approach an on-going kaggle competition, specifically bengali.ai: grapheme classification. This is a multi-label classification challenge with over 200K images. I will be using PyTorch to solve this problem. By the end of this tutorial you will be able to train any pre-trained model you want to train on this dataset! Competition page: https://www.kaggle.com/c/bengaliai-cv19 The video is in two parts. In this part, we will build the framework for training any pretrained model we want to train, add augmentations, write the training script and the models and build the final inference. Follow me on: Twitter: https://twitter.com/abhi1thakur LinkedIn: https://www.linkedin.com/in/abhi1thakur/ Kaggle: https://kaggle.com/abhishek